© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 34168
    Prev
    Next
    INDEX
    Explanations

    scientific Q&A and code definitions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    resulting
    -0.85
     houver
    -0.84
     ».
    -0.84
     imediatamente
    -0.82
     importantly
    -0.82
    Amended
    -0.81
     erreicht
    -0.81
     apaixon
    -0.80
    …"
    -0.79
    apatos
    -0.78
    POSITIVE LOGITS
    远处
    1.08
     regionales
    1.06
     kadın
    1.01
    IQUE
    0.99
     overzicht
    0.98
    ção
    0.98
    吅
    0.97
    onav
    0.97
    らせて
    0.97
    sehen
    0.96
    Activations Density 0.001%

    No Known Activations